batteries

Article
Integration of Computational Fluid Dynamics and Artificial
Neural Network for Optimization Design of Battery Thermal
Management System
Ao Li 1 , Anthony Chun Yin Yuen 1, * , Wei Wang 1 , Timothy Bo Yuan Chen 1 , Chun Sing Lai 2 , Wei Yang 3 ,
Wei Wu 4 , Qing Nian Chan 1 , Sanghoon Kook 1 and Guan Heng Yeoh 1

1 School of Mechanical and Manufacturing Engineering, University of New South Wales,

Sydney, NSW 2052, Australia; [email protected] (A.L.); [email protected] (W.W.);
[email protected] (T.B.Y.C.); [email protected] (Q.N.C.); [email protected] (S.K.);
[email protected] (G.H.Y.)
2 Brunel Interdisciplinary Power Systems Research Centre, Department of Electronic and Electrical Engineering,
Brunel University London, Kingston Lane, London UB8 3PH, UK; [email protected]
3 School of Energy, Materials and Chemical Engineering, Hefei University, 99 Jinxiu Avenue,
Hefei 230601, China; [email protected]
4 Department Materials Science and Engineering, City University of Hong Kong, Tat Chee Avenue,
Hong Kong 999077, China; [email protected]
* Correspondence: [email protected]; Tel.: +61-2-9385-5697

Abstract: The increasing popularity of lithium-ion battery systems, particularly in electric vehicles
and energy storage systems, has gained broad research interest regarding performance optimization,
thermal stability, and fire safety. To enhance the battery thermal management system, a compre-
Citation: Li, A.; Yuen, A.C.Y.;
hensive investigation of the thermal behaviour and heat exchange process of battery systems is
Wang, W.; Chen, T.B.Y.; Lai, C.S.;
paramount. In this paper, a three-dimensional electro-thermal model coupled with fluid dynamics
Yang, W.; Wu, W.; Chan, Q.N.;
Kook, S.; Yeoh, G.H. Integration of
module was developed to comprehensively analyze the temperature distribution of battery packs
Computational Fluid Dynamics and and the heat carried away. The computational fluid dynamics (CFD) simulation results of the lumped
Artificial Neural Network for battery model were validated and verified by considering natural ventilation speed and ambient
Optimization Design of Battery temperature. In the artificial neural networks (ANN) model, the multilayer perceptron was applied
Thermal Management System. to train the numerical outputs and optimal design of the battery setup, achieving a 1.9% decrease in
Batteries 2022, 8, 69. https://doi.org/ maximum temperature and a 4.5% drop in temperature difference. The simulation results provide a
10.3390/batteries8070069 practical compromise in optimizing the battery configuration and cooling efficiency, balancing the
Academic Editors: Carlos Ziebert layout of the battery system, and safety performance. The present modelling framework demon-
and Pascal Venet strates an innovative approach to utilizing high-fidelity electro-thermal/CFD numerical inputs for
ANN optimization, potentially enhancing the state-of-art thermal management and reducing the
Received: 7 June 2022
risks of thermal runaway and fire outbreaks.
Accepted: 7 July 2022
Published: 8 July 2022
Keywords: thermal management; lithium-ion batteries; CFD modelling; ANN; optimization design
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations. 1. Introduction
With recent advancements in electric technology as well as the growing global concern
of energy crisis and environmental pollution, a lot of research interests are devoted to
Copyright: © 2022 by the authors.
the search for alternative energy sources, including nuclear, wind, or solar energy. Bat-
Licensee MDPI, Basel, Switzerland. tery energy storage systems have caught the public eye due to their many advantages:
This article is an open access article fast responsiveness, controllability, structural independence, and widespread application
distributed under the terms and range [1]. Lithium-ion based battery energy storage systems have become the most com-
conditions of the Creative Commons petitive choice for various applications [2–5]. Lithium-ion batteries (LIBs) as a source of
Attribution (CC BY) license (https:// alternative energy through renewable energies have been proposed in industries for many
creativecommons.org/licenses/by/ portable consumer electronic devices, including cell phones and laptops. Moreover, LIBs
4.0/). have begun to enter the automotive market as power packs for hybrid and battery electric

Batteries 2022, 8, 69. https://doi.org/10.3390/batteries8070069 https://www.mdpi.com/journal/batteries

Batteries 2022, 8, 69 2 of 17

vehicles (HEVs and EVs) due to their enormous power, efficiency, and durability of a
charge cycle.
Temperature plays a critical role in many aspects of the performance of LIBs, includ-
ing charge acceptance [6], energy capability [7], reliability [8], and so on. In comparison
with other battery technologies, LIB performs relatively poor thermal stability, and many
accidents happened in recent years [9–11]. A typical LIB comprises four main components:
an anode, a cathode, a separator, and an electrolyte. All the parts form a closed system
separated from the air, so there is no explosion or fire danger at the normal working tem-
perature [12]. However, the abuse of LIB will generate the threat of thermal runaway and
overheating. Both positive and negative electrode decomposition are exothermic processes.
Also, oxygen can be generated during the decomposition reactions. The generated heat and
oxygen are the contributions to the combustion triangle. If the battery experiences harsh
working conditions during electric transportation, the generated heat triggers electrodes’
decomposition. As a result, the battery potentially faces thermal issues. Suppose the cell
temperature is rising over a certain threshold. In that case, a thermal runaway may turn up,
leading to a quick temperature rise and potentially other related undesirable consequences
such as the generation of toxic gas and smoke. With the rising battery temperature over a
critical point, the other chain exothermic reactions happen. The temperature and pressure
in the LIB are cumulated until it exceeds the battery endurance. Eventually, the fire and
rupture/explosion are inescapable. Therefore, the thermal management of LIB is essential
during the battery working process or battery application. It is also crucial to investigate
the LIB thermal runaway process by accurately monitoring and predicting temperature
dynamics during thermal propagation and implementing functional methods to improve
the cooling efficiency of the battery itself and the battery system.
There are two key topics of concern in battery thermal management: handling the
charge/discharge cycle and governing the battery heat growth [13,14]. Many pieces of research
focused on the battery thermal management system of EVs have been conducted [15–17]. The
heat produced during the operating process has been established as the major rise in the
working temperature. Computation Fluid Dynamics (CFD) is a practical tool for investigating
thermal properties and simulating multiple physics fields [18]. CFD simulations could provide
detailed information about the electrical and thermal areas inside the battery during the work
process that is often challenging to assess and extract by experimental approaches. Model-
based investigations promote a theoretical and comprehensive understanding of battery
physics beyond what is possible from practical methods only. For example, Kirad and
Chaudhari [19] applied numerical models for studying the selection of the battery module
spacing with an improvement in cooling performance. Due to the development of computing
capability, numerical simulations are gradually applied in battery models, battery components
and materials studies, and battery safety engineering [20–22]. Most numerical studies rely
on the thermal models, which predict the average surface temperature for a LIB cell [23–26],
and lots of experimental investigations on thermal propagation have been carried out [27–30].
Nevertheless, to achieve a proper estimation of the thermal behaviour of a battery, many
aspects, including the shape, layout, and physical and electrochemical properties, should
be illustrated as closely as possible in the simulation. For instance, the asymmetric surface
temperature of a battery cell should be considered in the model. The non-uniform temperature
distribution in the LIBs leads to an electrical imbalance, lower battery performance, and shorter
battery life [31,32]. Regarding the detailed temperature distribution, an electric-thermal model
with the non-uniform feature should be built.
Moreover, battery thermal management systems have been classified in various ways
based on different criteria [33–35]. For example, battery thermal management systems can
be branched into three kinds based on various mediums: air-based, liquid-based, and phase
change materials-based. Several optimization studies on the battery thermal management
system have been previously conducted [36–39]. The air-cooling method is considered the
most traditional approach and is a favoured option for HEVs and EVs. It is clear that the
optimization of battery packs or systems depends on many parameters, such as geometry
Batteries 2022, 8, x FOR PEER REVIEW 3 of 18

Batteries 2022, 8, 69 management system have been previously conducted [36–39]. The air-cooling method is
3 of 17
considered the most traditional approach and is a favoured option for HEVs and EVs. It
is clear that the optimization of battery packs or systems depends on many parameters,
such as geometry structure, coolant properties, operating conditions, and so force. Still,
structure, coolant properties, operating conditions, and so force. Still, few researchers focus
few researchers focus on multiple parameters simultaneously.
on multiple parameters simultaneously.
As a part of artificial intelligence, machine learning focuses on the study of accuracy
As a part of artificial intelligence, machine learning focuses on the study of accuracy
improvement by computer algorithms and data to imitate how humans learn [40,41]. The
improvement by computer algorithms and data to imitate how humans learn [40,41].
application of machine learning techniques, particularly artificial neural networks (ANN),
The application of machine learning techniques, particularly artificial neural networks
can be a potential method to optimize the battery system. Because LIBs are highly com-
(ANN), can be a potential method to optimize the battery system. Because LIBs are highly
plex, nonlinear
complex, nonlinearsystems, applying
systems, a probabilistic
applying approach
a probabilistic approachallows for quantification
allows of un-
for quantification of
certainty, which positively impacts making decisions in design and
uncertainty, which positively impacts making decisions in design and control. ANN model control. ANN model
is
is a
a kind
kind ofof model
model that
that characterizes
characterizesthe theinterrelation
interrelationbetween
betweeninputs
inputsandandoutputs
outputsbybyusing
usinga
acollection
collection of interconnected nodes (perceptron). The application of ANN
of interconnected nodes (perceptron). The application of ANN to battery research to battery re-
search is still relatively new. Wu et al. [42] generated a design map
is still relatively new. Wu et al. [42] generated a design map that fulfills both specificthat fulfills both spe-
cific
energyenergy
and and specific
specific powerpower requirements
requirements using
using a asystematic
systematicapproach
approachbased
based onon ANN.
ANN.
Qian
Qian etet al.
al. [43]
[43] optimized
optimized the the battery
battery spacing
spacing by by neural
neural network
network model
model andand demonstrated
demonstrated
the interrelationship between
the interrelationship between layoutlayout and
and temperature
temperature of of battery
battery packs.
packs. Feng
Feng etet al. [44]
al. [44]
developed an electrochemical-thermal-neural-network method used
developed an electrochemical-thermal-neural-network method used for the co-estimation for the co-estimation
of
of LIB
LIB state
stateof ofcharge
charge(SOC)
(SOC)and andstate of of
state temperature.
temperature. Shi Shi
et al.
et[45] applied
al. [45] the fully
applied con-
the fully
nected deep network approach to study air-based cooling LiFePO
connected deep network approach to study air-based cooling LiFePO4 cuboid battery packs 4 cuboid battery packs
and
and optimize
optimizethe theU-type
U-typestructure.
structure. However,
However, pioneering
pioneeringstudies havehave
studies highlighted the pos-
highlighted the
sibility of using
possibility ANN
of using ANNfor battery thermal
for battery problems.
thermal These
problems. studies
These include
studies modelling
include bat-
modelling
tery spacing,
battery spacing, specific format,
specific format, and
andsome
somebattery
batteryperformances.
performances.The Thedetailed
detailed temperature
temperature
distribution of LIB and battery pack have not been fully investigated. Besides, the ambient
temperature and natural ventilation should be considered during the battery working
process. Therefore,
process. Therefore,the thecombination
combinationbetweenbetweenANN ANN analysis
analysis andandthethe electro-thermal
electro-thermal bat-
battery
tery
model model is proposed
is proposed to investigate
to investigate furtherfurther the battery
the battery system’ssystem’s
coolingcooling efficiency
efficiency and
and battery
battery
fire safetyfireperformance.
safety performance. Figure the
Figure 1 shows 1 shows the schematic
schematic figure of thefigure of the CFD-ANN
integrated integrated
CFD-ANN
model proposed modelinproposed
this study. in this study.

Figure 1. Schematic
Figure 1. Schematic of
of the
the proposed CFD-ANN model.
proposed CFD-ANN model.

To this end,
To this end, the
the non-uniform
non-uniform distributions
distributions ofof the
the battery
battery cell
cell should
should be
be investigated
investigated
for the
the thermal
thermalanalysis,
analysis,which
whichcancan
be treated as a measurement and prediction at theatearly
be treated as a measurement and prediction the
early stage
stage of the of the Li-ion
Li-ion batterybattery
thermalthermal
runaway runaway fires. Furthermore,
fires. Furthermore, with thewith the numerical
numerical analysis,
a better understanding of battery pack configuration design can be achieved. In this article,
the contributions are:
Batteries 2022, 8, 69 4 of 17

(i) Establishment and development of a three-dimensional electro-thermal model capable

of considering temperature distribution of battery packs and heat exchange with the
ambient environment.
(ii) Utilize the numerical results to comprehensively describe and predict the battery
system’s thermal behaviour to improve battery safety during the designing and
working stages.
(iii) Coupled the electro-thermal model with the ANN model to optimize the battery sys-
tem configuration design and enhance the cooling performance of the battery system.
The outline of this paper is summarized as follows: Section 2 introduces the numerical
models applied in this paper, including electrochemical model, thermal model, and ANN
model. Section 3 demonstrates the numerical results of the proposed model with validation
and verification. Also, the training process and optimization results are listed in this section.
Finally, the author presented some conclusions and proposed the future perspectives on
this field in the conclusion section.

2. Numerical Models Applied in the Battery Pack

2.1. Electrochemical Model
The electrochemical model applied in this study could be seen as a lumped version
of a single particle model [46], simulating the transport of intercalated lithium in one of
the electrodes. The single particle model predicts the temperature distribution and voltage
changes in a single LIB cell during galvanostatic operations. The simplification of this
model can be conducted when the battery is mainly controlled by the diffusion process
in one of the electrodes only. The model is based on a complete model of a LIB working
process cycle [47]. In this model, the lumped battery interfaces are utilized, and the battery
cell voltage Ecell is calculated by applying time-dependent cell current Icell . Additionally,
the battery open circuit voltage data, named EOCV , is estimated from SOC.
The three-dimensional electro-thermal model built in this paper is based on a typical
cylindrical LiFePO4 /Carbon power battery, considering the physical and electrical conser-
vations, as well as thermal principles and electrochemical kinetics. The electrochemical
reactions of common LIBs can be described as the following Equations (1)–(3), where M
stands for a metal, which is used as a cathode material such as cobalt or nickel, and C is
recognized as the anode materials.
The reaction at the positive electrode is described as:

LiMO2 ↔ Li1− x MO2 + xLi+ + xe− (1)

The chemical reaction at the negative electrode is expressed as:

C + xLi+ + xe− ↔ Li x C (2)

The overall reaction can be presented as:

LiMO2 + C ↔ Li1− x MO2 + Li x C (3)

Figure 2 demonstrates the working process of a typical LIB, and the fundamental cell
unit is considered a sandwich structure, including the positive electrode, the separator,
the negative electrode, and the current collectors located at both electrodes. The metal
tab is joined at each correlated current collector and electrode. The separator is located
between cathode and anode, a porous polymer membrane to prevent physical contact of
electrodes. The electrolyte is the medium that enables the ion transport mechanism between
electrodes. It requires specific working conditions, such as significant ion conductivity, low-
set electrical conductivity, extended temperature range of operation, thermo-dynamically
stable at a certain range of voltages, environmentally friendly, etc.
Batteries 2022,
Batteries 2022, 8,
8, 69
x FOR PEER REVIEW 55 of
of 17
18

Figure 2. The principle of operation for a typical LIB and its structure.

Each
Each electrode
electrode and
and separator is impregnated
separator is impregnated with with electrolyte,
electrolyte, achieving
achieving transporta-
transporta-
tion of lithium ions. The material parameters for the electrolyte refer to
tion of lithium ions. The material parameters for the electrolyte refer to a plasticized a plasticized
eth-
ethylene carbonate/dimethyl carbonate (EC/DMC) electrolyte remaining
ylene carbonate/dimethyl carbonate (EC/DMC) electrolyte remaining in a polymer in a polymer
matrix.
matrix. Therefore,
Therefore, theelectrolyte
the stated stated electrolyte
volumevolume
fractionfraction
points topoints to this model’s
this model’s totalelectro-
total liquid liquid
electrolyte and polymer matrix volume fractions. In this model, the potential
lyte and polymer matrix volume fractions. In this model, the potential losses ηIR due losses η IR dueto
to ohmic and charge transfer processes are given
ohmic and charge transfer processes are given as follows: as follows:

𝐼
Icell
η IR𝜂 ==η IR,1C
𝜂 , (4)
𝐼
I1C

where ηηIR,1C
IR,1Crepresents
representsthethe
potential
potential losses under
losses underthe the
1C current. The 1C
1C current. current
The I1C means
1C current I1C
that thethat
means discharge current will
the discharge discharge
current the entirethe
will discharge battery
entireinbattery
one hour, and hour,
in one it is calculated
and it is
as:
calculated as:
Qcell,0
I1C = 𝑄 , (5)
𝐼 = 3600 s (5)
3600 s
The dimensionless charge exchange current J0 is applied for the integrated voltage
The dimensionless
dissipation accompaniedchargeby the exchange currentreactions
charge delivery J0 is applied
on thefor
twotheelectrodes’
integratedsurfaces,
voltage
dissipation
shown as: accompanied by the charge delivery reactions  on the two electrodes’ surfaces,
shown as: 2RT Icell
ηact = asinh (6)
F2𝑅𝑇 2J0 I𝐼1C
The diffusion processes also𝜂lead=to 𝐹 𝑎 𝑠𝑖𝑛ℎ loss, which is represented by η . De-
potential 2𝐽 𝐼 act
(6)
rived from diffusion in an idealized particle or by applying a resistor-capacitor combination,
The diffusion processes also lead to potential loss, which is represented by ηact. De-
concentration overpotential effects can be explained among the lumped battery interfaces.
In thisfrom
rived model,diffusion indiffusion
particle an idealized particle or Fickian
is calculated. by applying a resistor-capacitor
diffusion of a dimensionless combina-
SOC
tion, concentration overpotential effects can be explained
parameter is calculated in this case, using spherical symmetry, according to:among the lumped battery in-
terfaces. In this model, particle diffusion is calculated. Fickian diffusion of a dimensionless
SOC parameter is calculated in this ∂SOCcase, using spherical symmetry, according to:
τ = −∇·(−∇SOC ) (7)
𝜕𝑆𝑂𝐶
∂t
𝜏 = −𝛻 ∙ −𝛻𝑆𝑂𝐶 (7)
The interval stands for a common 𝜕𝑡particle of the electrode controlling the cell, where
X = 0The X = 1 mean
andinterval thefor
stands particle
a commoncentreparticle
and particle
of the surface
electrodeaccordingly.
controlling the cell, where
The operating conditions at the particle boundary are
X = 0 and X = 1 mean the particle centre and particle surface accordingly. as follows:
The operating conditions at the particle boundary are as follows:
∇SOC = 0| X =0 (8)
𝛻𝑆𝑂𝐶 = 0|  (8)
τI𝜏𝐼cell 
∇SOC = (9)

𝛻𝑆𝑂𝐶 =Nshape Qcell,0  (9)

𝑁 𝑄 , X =1
where Nshape equals three for spherical particles in this model. The SOC of the surface,
SOCsurface , is identified at the particle surface. The average SOC, named SOCaverage , is
Batteries 2022, 8, 69 6 of 17

prescribed by lumping the particle volume, appropriately considering spherical coordinates,

and is defined as:
R1 1
SOC4 ∏ X 2 dX Z
SOCaverage = 0
R1 = 3 SOCX 2 dX (10)
0 4 ∏ X dX
2
0

The integrated voltage dissipation accompanied by concentration overpotential is

represented by η conc and defined as:
 

ηconc = Eocv SOCsur f ace − Eocv SOCaverage (11)

Lastly, the battery cell voltage Ecell is defined as:

Ecell = Eocv SOCaverage + η IR + ηact + ηconc (12)

Establishing the explanation of η conc and Ecell is also calculated as:

 
Ecell = Eocv SOCsur f ace + η IR + ηact (13)

The battery model involves these three steps. At first, a lumped battery model is
set up and run for a time-dependent battery current. Then, parameter estimation of the
parameters η IR ,1C , τ, and J0 is demonstrated using experimental data. This is achieved
using the Global Least-Squares Objective node in the optimization interface, combined with
the optimization study step using a Levenberg-Marquardt optimization solver. Lastly, cell
voltage prediction is performed using the optimized lumped parameter values obtained in
the previous parameter estimation study compared with experimental data.

2.2. Thermal Model

In this study, the thermal model is based on a previous two-dimensional axial symme-
try approach, simulated by the Heat Transfer in Solids module. A spirally wound type of
battery is chosen for this simulation, and the simplification of the heat conduction can be
achieved along the spiral direction. Moreover, instead of simulating the heat conduction
in each layer along the radial direction, the wound sheets are acted as a combination cell
material domain. These approximations are understandable for spiral wound battery cells
cooled under natural convection. The model configuration comprises three connection
sections: (1) Battery outer can; (2) A combination cell material domain; (3) Center axis
(mandrel where the battery cell sheets are wound).
For this model, several equations and parameters are considered. Considering the
anisotropic thermal conductivities in this model and differences among various direc-
tions [48], the thermal conductivities along the radial path, kT,r , and along the cylinder
length direction, kT,ang , are defined separately as follows:

∑ Li
k T,r = (14)
∑ i /k T,i
L

∑ Li k T,i
k T,ang = (15)
∑ Li
The density ρbatt and heat capacity C p,batt for the combination cell material domain is
defined as stated by the following equations:

∑ Li ρi
ρbatt = (16)
∑ Li

∑ Li C p,i
C p,batt = (17)
∑ Li
Batteries 2022, 8, 69 7 of 17

The heat source produced by the combination cell material domain is identified by
employing the Electrochemical Heating Multiphysics coupling module. However, the heat
source term in the combination cell material domain is scaled to solve the lack of heat
generation in the current collectors and the canister thickness. This mounted heat source
is acquired by multiplying two factors of the volumetric heat source from the 1D Li-ion
battery model. The former factor is the fraction of the total 1D model in which heat is
produced. That is the total length value of electrodes and the separator, divided by the total
battery length, including the measurements of both current collectors. The latter factor is
the fraction of the entire 3D cylindrical battery. The volume in which heat is produced is
the cell’s total volume, including the homogenized wound layers of the cell material, the
centre axis, and the battery case, minus the volume of the outer case and the volume of
the battery centre axis. This heat source is then divided by the total volume of the battery
cell domain, which is the difference between the whole battery volume and the centre axis
volume. Thereby, the following equation for the 3D heat source is demonstrated:

Lneg + Lsep + L pos ((rbatt − dcan )2 − r2 mandrel )(hbatt − 2dcan )

Qh,3D = Qh,1D (18)
Lbatt (r2 batt − r2 mandrel )hbatt

For the lumped battery interface model, Arrhenius expression is applied to model
each battery cylinder, with temperature-dependent ohmic, exchange current, and diffusion
time-constant parameters.
The thermal conductivity in the combination cell material domain is anisotropic due to
the spiral type of the battery. The orthotropic thermal conductivity in the combination cell
material domain is solved by introducing a cylindrical coordinate system in the model. The
zero-Mach-number limit of the compressible conservation equations was applied to depict
the flow movement and heat transfer. Regarding the enthalpy equation and the temperature
equation, the energy conservation for incompressible fluid can be simplified to:

∂T
ρC p + ρC p v·∇ T = ∇·(k∇ T ) + Q (19)
∂t

2.3. ANN Model

ANN has rapidly developed in recent decades as a common tool to model a broad
range of engineering systems due to its capability to learn and adapt to find potential
correlations among different properties, mainly to map the nonlinear relationship of inputs
and outputs. A hidden layer is a layer located between the input and output of the ANN
model, in which artificial neurons applies a set of weights to the inputs and directs them
through an activation function as the output. Hidden layers of ANN allow for a neural
network’s function to be taken apart for specific data transformations. For example, images
and documents are treated as initial inputs from external data. The ultimate outcomes
complete the task, such as recognizing objects in a snap.
A typical ANN model compromises five main components: inputs, summation func-
tions, weights, activation functions, and outputs. The artificial neuron in the hidden layer
works as a biological neuron in the brain. To form a directed, weighted graph, the network
is formed by linking the output of specific neurons to the input of other neurons. A learning
process can adapt the activation functions and weights. The learning rule or training
approach controls the certain learning process. The summation function (denoted by E) is
a function that calculates the net inputs, considering adjustable weights wij and bias wbi ,
expressed as:
n
E= ∑ wij x j + wbi (20)
j =1

The activation function of a node governs the output of that node, or “neuron,”
provided input or set of inputs. The activation function presents a functional relationship
between the input and output layers. Some frequently applied activation functions are step
Batteries 2022, 8, 69 8 of 17

activation, threshold function, sigmoid function, and hyperbolic tangent function [49]. The
logistics sigmoid function is adopted in this study and is presented as:

1
f ( E) = (21)
1 + e− E
The number of hidden neurons determined by the formulation according to neural
network design [50] is given by:

Ns
Nh = (22)
(α( Ni + No ))

where the subscripts h denotes the number of input neurons, s is the sample amount in the
training dataset, o is the number of outputs, and α is a scaling factor ranging from 2–10. In
this study, α is prescribed as 2 to achieve an optimal solution without overfitting, and ten
hidden neurons were applied in the ANN model.

3. Results and Discussions

3.1. Electro-Thermal Model Simulation Results
In this paper, a corporate software applied finite element, COMSOL Multiphysics 5.5,
was employed to study the three-dimensional electro-thermal coupled model. The default
mesh component was applied for generating the mesh, and mesh independence was exam-
ined as well. The MUMPS time-dependent solver was applied for battery variables, and the
PARDISO solver was chosen for heat transfer variables. The mesh applied for this study
consists of triangular and quadrilateral elements developed by COMSOL Multiphysics 5.5.
In order to obtain the thermal behaviour and boundary layer spread, the refined mesh is
achieved at the connections of the battery boundary. Mesh independence verification was
performed to avoid the grid number and mesh quality impact on the simulation results,
shown in Table 1. According to Table 1, 43,486 elements show reliable and efficient results,
and more elements lead to larger computation time. Therefore, the total number of meshes
is about 43,486 elements chosen for the validation case, considering the efficiency and
accuracy. For the battery pack simulation, the most appropriate grid amount is around
211,907 elements. Subsequently, more simulation results are produced to feed the machine
learning model to training.

Table 1. This is a table. Tables should be placed in the main text near to the first time they are cited.

Grid Resolution Elements Number Calculation Time Maximum Electrolyte Temperature

Finer 114,273 75.6 min 20.250 ◦ C
Fine 43,486 30.5 min 19.829 ◦ C
Normal 23,986 18.7 min 19.810 ◦ C
Coarse 9708 10.6 min 18.910 ◦ C

The validation of the electrochemical model and thermal model is established on the
Type 38,120 battery cell, in which the nominal voltage is 3.2 V and capacity is 10 Ah, as
well as the thickness of the cathode, the separator, and the anode are 91 µm, 40 µm and
142 µm, respectively. The type we choose is one of the most commonly used in the current
commercial market. It is developed based on physical and electrical conservations, as
well as thermal principles and electrochemical kinetics. The battery pack investigation
for the three-dimensional electro-thermal model is built by Type 21,700 battery cylinders
with a nominal capacity of 4 Ah and a nominal voltage of 3.6 V. The battery pack is
constructed by coupling two cylindrical batteries in parallel. Then the mated battery pairs
are connected in series. The geometry and battery parameters are listed in Table 2. The
geometry specifications are used to build the battery domain for thermal simulations, while
the battery parameters are applied for the simulation of the electrochemical model.
Batteries 2022, 8, 69 9 of 17

Table 2. Geometry dimension and electrochemical parameters of the battery cell.

Geometry Parameters Battery Parameters

C_rate 4 C rate
d_batt 21 [mm] Battery diameter
Q_cell 4 [A·h] Battery cell capacity
I_1C Q_cell/1 [h] 1C current
r_batt d_batt/2 Battery radius
kT_batt_ang 30 [W m−1 K−1 ] Thermal conductivity, in plane
kT_batt_r 1 [W m−1 K−1 ] Thermal conductivity, cross plane
h_batt 70 [mm] Battery height
Ea_eta1C 24 [kJ mol−1 ] Activation energy
Ea_J0 −59 [kJ mol−1 ] Activation energy
h_term 1 [mm] Terminal thickness
Ea_Tau 24 [kJ mol−1 ] Activation energy
T0 20 [◦ C] Reference temperature
r_term 3 [mm] Terminal radius
J0_0 0.85 J0 at reference temperature
Serial connector tau_0 1000 [s] tau at reference temperature
d_sc 2 [mm]
depth eta_1C 4.5 [mV] eta_1C at reference temperature
Serial connector rho_batt 2000 [kg m−3 ] Battery density
h_sc 1 [mm]
height Cp_batt 1400 [J kg−1 K−1 )] Battery heat capacity
Parallel connector ht 30 [W m−2 K−1 ] Heat transfer coefficient
h_pc 0.5 [mm]
height T_init 20 [◦ C] Initial/external temperature
Parallel connector
w_pc 1 [mm]
width

The initial battery state is fully charged. The discharge process at different current
densities is simulated, and the discharge curves during the process are demonstrated.
The battery capacity under various discharge rates is built through the modelling. The
simulation will be stopped when the cell potential decreases under 3 V, which is the
state of end-of discharge. The simulation result of the nominal discharge current density
representing case 1C, is shown in Figure 3a. The numerical result shows a good agreement
with the experiment data. Meanwhile, there are a few deviations in the usual discharge
voltage plateau related to the thermodynamic analytics and battery prototypes. The thermal
model is validated, and the results are shown in Figure 3b. The experimental data is
extracted from the surface of the battery along the axis to track the surface temperature
development. The simulation results in the same location of the testing point have similar
growth trends. The slight difference between the experimental and numerical results is
because of the temperature rise of the experiment due to the local ohmic heat generation,
where the electrical contact resistance among the connectors and terminals of the battery.
Considering the electrochemical performance, the current flows inside the battery cell
and battery pack remain similar due to applying a single particle model. The Single Particle
Battery interface answers for solid diffusion in the electrode particles and the intercalation
reaction kinetics. A lumped solution resistance term is used for covering the ohmic potential
drop inside the electrolyte. The cell capacity is specified through fractional volumes of
both electrodes in the battery. The individual electrode operational state-of-charges are
used to identify the initial charge distribution in the battery. The temperature contour and
heat flux streamline of the proposed battery pack shows the temperature distribution on
the whole battery pack during its working process by the proposed electro-thermal model.
The maximum temperature of the battery’s innermost parts is around 2 ◦ C higher than
the outermost parts. It also provides the temperature difference of the whole battery pack.
With the utilization of this lumped model, the broad temperature distribution of battery
cell surfaces can be represented. Besides, the heat flux generated inside the battery cell
can be simulated, as well as the heat exchange between battery surfaces and the ambient
cooling air can be simulated numerically.
 perature distribution on the whole battery pack during its working process by the pro-
posed electro-thermal model. The maximum temperature of the battery’s innermost parts
is around 2 °C higher than the outermost parts. It also provides the temperature difference
of the whole battery pack. With the utilization of this lumped model, the broad tempera-
ture distribution of battery cell surfaces can be represented. Besides, the heat flux gener-
Batteries 2022, 8, 69 10 of 17
ated inside the battery cell can be simulated, as well as the heat exchange between battery
surfaces and the ambient cooling air can be simulated numerically.

Figure 3. Comparison of numerical results of working voltage (a) and temperature (b) with experi-
Figure 3. Comparison of numerical results of working voltage (a) and temperature (b) with experi-
mental
mental results
results [23]
[23] during
during 1C1C galvanostatic
galvanostatic discharge
discharge under
under natural
natural convection
convection conditions.
conditions.

Through the numerical study for the whole battery pack, the configuration setup
Through the numerical study for the whole battery pack, the configuration setup of
of the battery pack is also investigated. The two-dimensional parameters are defined by
the battery pack is also investigated. The two-dimensional parameters are defined by dif-
different directions with various gaps, which are no gap (0 m), half of a cell (0.01 m) and one
ferent directions with various gaps, which are no gap (0 m), half of a cell (0.01 m) and one
cell (0.02 m). Through permutation and combination, nine sets of collocations are formed.
cell (0.02 m). Through permutation and combination, nine sets of collocations are formed.
Figure 4 shows that all the battery cells are constructed together with various gap setups
Figure 4 shows that all the battery cells are constructed together with various gap setups
among the parallel-coupled battery pairs, which are the first nine cases. The gap enhances
among the parallel-coupled battery pairs, which are the first nine cases. The gap enhances
the convective and conductive between battery cells and ambient air from the battery safety
theperspective,
convective improving
and conductive between battery cells and ambient air from the battery
battery pack cooling efficiency and fire safety.
safety perspective, improving battery
To further understand the battery pack cooling efficiency
temperature and fire
distribution, air safety.
velocity and ambient
environment are considered as well. Buoyancy forces cause natural convection as a con-
sequence of density changes ascribed to temperature differences in the fluid. At heating,
the fluid will rise because of the density variation in the boundary layer. Meanwhile, the
cooler fluid, which will heat and increase, will replace the raised fluid. This continuous
phenomenon is named free or natural convection. Thus, this study selected four sets of air
velocity. Moreover, the temperature difference (The difference between the highest and the
lowest temperature of the battery pack) and maximum temperature (The maximum tem-
perature of a battery cell) are also considered. Figure 5 plots the maximum temperature and
temperature difference profiles under various operating conditions, where the geometry
conditions remain the same. From Figure 5a,c, air velocity positively impacts decreasing the
maximum temperature and temperature difference. Under the same ambient temperature,
shown in Figure 5b, increasing the air velocity can enhance the cooling efficiency, but the
Batteries 2022, 8, 69 11 of 17

drop in maximum temperature is not much. Figure 5c, cases with air velocity 4 m s−1
achieve 36%, which is the maximum percentage of temperature difference drop compared
to other cases in this configuration. It is demonstrated that when the minimum values of
maximum temperature and temperature difference are reached, the format set up
Batteries 2022, 8, x FOR PEER REVIEW 11 ofis18the
best and optimization results.

Batteries 2022, 8, x FOR PEER REVIEW 12 of 18

Figure 4. Temperature contours of different battery pack configurations.
Figure 4. Temperature contours of different battery pack configurations.
To further understand the battery temperature distribution, air velocity and ambient
environment are considered as well. Buoyancy forces cause natural convection as a con-
sequence of density changes ascribed to temperature differences in the fluid. At heating,
the fluid will rise because of the density variation in the boundary layer. Meanwhile, the
cooler fluid, which will heat and increase, will replace the raised fluid. This continuous
phenomenon is named free or natural convection. Thus, this study selected four sets of air
velocity. Moreover, the temperature difference (The difference between the highest and
the lowest temperature of the battery pack) and maximum temperature (The maximum
temperature of a battery cell) are also considered. Figure 5 plots the maximum tempera-
ture and temperature difference profiles under various operating conditions, where the
geometry conditions remain the same. From Figure 5a,c, air velocity positively impacts
decreasing the maximum temperature and temperature difference. Under the same am-
bient temperature, shown in Figure 5b, increasing the air velocity can enhance the cooling
efficiency, but the drop in maximum temperature is not much. Figure 5c, cases with air
velocity 4 m s−1 achieve 36%, which is the maximum percentage of temperature difference
drop compared to other cases in this configuration. It is demonstrated that when the min-
imum values of maximum temperature and temperature difference are reached, the for-
mat set up is the best and optimization results.

Figure 5. The profile of maximum temperature (a) and temperature difference (b,c) under various
Figure 5. The profile of maximum temperature (a) and temperature difference (b,c) under various
operation conditions.
operation conditions.
3.2. Training and Results Analysis
In this study, the multilayer perceptron (MLP) neural network was applied. It is one
of the most competitive types of ANN for regression in various research fields. Because
this approach shows a considerable capability for universal approximation, it is regularly
Batteries 2022, 8, 69 12 of 17

3.2. Training and Results Analysis

In this study, the multilayer perceptron (MLP) neural network was applied. It is one
of the most competitive types of ANN for regression in various research fields. Because
this approach shows a considerable capability for universal approximation, it is regularly
applied to model quite highly complex and disordered phenomena. As mentioned pre-
viously, the ANN utilizes the battery thermal distribution simulation dataset obtained
through numerical simulations of a typical battery pack configuration on two cylindrical
batteries in parallel and six-coupled battery pairs in series. In summary, it consists of
130 data sets of six parameters (four inputs and two outputs) prepared for the training
and testing of the ANN. The detailed inputs and outputs of each dataset are illustrated
in Table 3. Note that the heat transfer coefficient was replaced with the air velocity more
effectively presentative by the ANN. It is possible to extend the ANN model to predictions
on other heat transfer methods not considered in the datasets by analyzing their coolant
velocity. The heat transfer coefficient of air can be estimated to:

ht = 10.45 − v − 10v1/2 (23)

where ht represents the heat transfer coefficient, and v is the relative speed between the
object exterior and air. This equation is empirical and can be applied to the velocity range
from 2 to 20 m s−1 [51].

Table 3. Details of the inputs and outputs for the ANN model.

Inputs Outputs
Air Ambient Maximum Temperature
Parameters X_Gap Y_Gap
velocity temperature temperature difference
Units m m m s−1 ◦C ◦C ◦C

Range 0–0.02 0–0.02 30–39.96 20–30 - -

The proposed ANN model has been trained using the Levenberg-Marquardt (LM)
optimization technique [52]. The LM method based on Levenberg [53] and Marquardt [54]
combines Newton’s method and gradient descent. It is one of the most efficient training
algorithms for neural network modelling [55]. Generally, this algorithm demands more
storage space but less time. The training process will be terminated spontaneously when
generalization ends improving, as represented by a growth of the mean square error of the
validation samples. In the LM method, the Hessian matrix can be approximated as:

Hf = JfTJf (24)

The gradient is given by:

∇ f = J f Te (25)
where Jf is the Jacobian matrix and e is the vector of a network error.
The LM working function or the fitness function is based on the mean square error
(MSE) between the network output and the target output:

N
1
∑

2
F = MSE = Ri,network − Ri,target (26)
N i =1

where N is the number of datasets, Ri,network is the network output and Ri,target is the target
output from the simulation data. The number of hidden neurons has been mentioned in
Equation (22).
Figure 6 demonstrates the ANN regression results, and it plots the regression relation
between the physical outputs and the targets, which indicates that this ANN model has
achieved a good fit with the training datasets. From Figure 7, the error histogram plot
Batteries 2022, 8, 69 13 of 17

shows that most errors reside in the range of −0.03688 to 0.0292. The majority of the
predictions had a root mean square (RMS) error of approximately 0.088%, with around
10% of the predictions within ±25% RMS error. The ANN was successfully trained with
an overall R (fitness) of 0.999, with most prediction errors within 1% RMS error. In future
works, the ANN model can be further refined to achieve an even higher reliability and
Batteries 2022, 8, x FOR PEER REVIEW 14 of 18
accuracy. This can be done by adding more simulation results considering a wider range of
configurations or applying more advanced ANN training techniques.

Regressionresults
Figure6.6.Regression
Figure resultsof
ofANN
ANNmodel.
model.

3.3. Optimization Analysis and Discussions

The optimization configuration was proposed further to investigate the designed
system with various working temperatures to improve the battery system’s fire safety
performance and cooling efficiency. These simulation results investigated the air velocity
and ambient temperature after successfully training the ANN model. A battery pack
comprises many single battery cells, and the operation temperature difference for the
single battery cell inside the battery pack will be sourced by the temperature imbalance
of the battery pack. This will result in the cell’s inconsistency, and over the normal state
during the charge and discharge process, harm the battery pack service life. Consequently,
an appropriate battery thermal management system should simultaneously lower the
maximum temperature and temperature difference of the battery packs to ensure the
reliability and consistency of EVs and HEVs battery performance.
The 6,250,000 groups of structure and operation features were created in MATLAB.
Inputs 1 and 2 are the configuration features, and Inputs 3 and 4 are the operating con-
ditions. The CFD-ANN model calculates the optimal combination to achieve the perfect
battery performance under the existing case arrangement with the current four inputs and
two outputs.

Figure 7. RMS error histogram of the ANN model predictions.

3.3. Optimization Analysis and Discussions

Batteries 2022, 8, 69 14 of 17
Figure 6. Regression results of ANN model.

Batteries 2022, 8, x FOR PEER REVIEW 15 of 18

ambient temperature after successfully training the ANN model. A battery pack com-
prises many single battery cells, and the operation temperature difference for the single
battery cell inside the battery pack will be sourced by the temperature imbalance of the
battery pack. This will result in the cell’s inconsistency, and over the normal state during
the charge and discharge process, harm the battery pack service life. Consequently, an
appropriate battery thermal management system should simultaneously lower the maxi-
mum temperature and temperature difference of the battery packs to ensure the reliability
and consistency of EVs and HEVs battery performance.
The 6,250,000 groups of structure and operation features were created in MATLAB.
Inputs 1 and 2 are the configuration features, and Inputs 3 and 4 are the operating condi-
tions. The CFD-ANN model calculates the optimal combination to achieve the perfect bat-
tery performance under the existing case arrangement with the current four inputs and
Figure7.
Figure RMSerror
7.RMS errorhistogram
histogramof ofthe
theANN
ANNmodelmodelpredictions.
predictions.
two outputs.
After
After successful
successful training
training the
the ANN
ANN model,
model, four
four inputs
inputs were
were divided
divided into
into 5050 intervals
intervals
3.3. Optimization Analysis and Discussions
separately in a specific
specific range. Then,
Then, 6,250,000
6,250,000 groups
groups of of structure
structure features
features were
were processed
processed
The optimization
in MATLAB, configuration was
and the optimal proposed further to investigate the designed sys-
optimal result
result can
can be selected.
selected. According
According to to Figure
Figure 8, 8, the
the batteries’
batteries’
tem with
maximum various working temperatures to improve the battery system’s fire safety per-
maximum temperature
temperatureand andtemperature
temperature difference
differenceareare
greatly affected
greatly by the
affected bybattery con-
the battery
formance
configuration and operating conditions, with a fluctuation as high as about 7 C forand
figuration and
and cooling
operatingefficiency. These
conditions, simulation
with a results
fluctuation as investigated
high as about the7 air
°C velocity
for ◦ the max-
the
imum
maximum temperature and and
temperature 1.5 °C ◦ Cthe
1.5for for temperature
the temperature difference. It can
difference. be obtained
It can be obtained thatthat
the
instability of the
the instability maximum
of the maximum temperature
temperature shows a different
shows trend
a different with
trend thethe
with fluctuation
fluctuation of
the temperature
of the temperaturedifference under
difference the current
under range
the current of various
range inputs.
of various Therefore,
inputs. the max-
Therefore, the
imum
maximumtemperature is chiefly
temperature influenced
is chiefly by theby
influenced battery properties.
the battery The temperature
properties. The temperature differ-
difference
ence can becan be treated
treated as an as an indicator
indicator to evaluate
to evaluate the battery
the battery cooling
cooling performance
performance of theofbat-
the
battery
tery pack.
pack.

Figure
Figure 8.
8. (a)
(a) Maximum
Maximum temperature
temperature and
and (b)
(b) temperature
temperature difference
difference of
of the
the battery
battery pack
pack for
for different
different
input combinations.
input combinations.

From
From the
the CFD-ANN
CFD-ANN model
model simulation
simulation results,
results, the
the six
six million
million sample
sample results
results were
were
sorted in ascending order of the battery spacing. Regarding achieving a battery cooling
sorted in ascending order of the battery spacing. Regarding achieving a battery cooling
performance, it can be concluded that the optimal case is the 0.02 m X-direction gap and
0.01 m Y-direction gap under 20 °C ambient temperature and the air velocity 16 m s−1.
Compared to the original configuration with the same operating conditions, the maxi-
mum temperature decreased by 1.9%, and the temperature difference dropped by 4.5%,
Batteries 2022, 8, 69 15 of 17

performance, it can be concluded that the optimal case is the 0.02 m X-direction gap and
0.01 m Y-direction gap under 20 ◦ C ambient temperature and the air velocity 16 m s−1 .
Compared to the original configuration with the same operating conditions, the maximum
temperature decreased by 1.9%, and the temperature difference dropped by 4.5%, which
means the CFD-ANN model optimization improved both the cooling efficiency and battery
performance. The proposed framework demonstrates an efficient way to improve the
thermal performance of the battery pack by optimizing the configuration under different
operating conditions.

4. Conclusions
The optimal design of battery thermal management systems was achieved by apply-
ing a three-dimensional electro-thermal model coupled with the ANN model. Utilizing
numerical simulations via CFD, different battery pack configurations were investigated
in a simulation environment to positively impact cooling efficiency, battery performance,
and battery fire safety. The three-dimensional electro-thermal model was introduced to
calculate the temperature distribution and validated with the previous experimental data.
The numerical case studies were applied to train the proposed ANN model, demonstrating
the relationship among geometric parameters, operating conditions and cooling efficiency.
The CFD-ANN model compared 6,500,000 combinations with various configuration and
boundary conditions. The optimal design for the current battery setup was the case with
a 0.02 m X-direction gap and a 0.01 m Y-direction gap, which lowered the maximum
temperature and temperature difference by 1.9% and 4.5%, respectively.
The results highlighted one significant advantage of numerical simulations. All the
pertinent information such as structural parameters and operation requirements can be
derived from the model. Furthermore, different factors can be simulated and optimized
simultaneously in a simulation environment to deliver a constructive perception of the
battery performance and thermal behaviour. In the future, more parameters can be intro-
duced with the current CFD-ANN model, such as electrode materials, electrolyte materials,
cell numbers, different coolants, and so forth. A universal database of parameters and
repercussions for the battery thermal management system can be prepared, which can then
be processed by foresight models to create outlooks and predictions of the fire risks of the
LIB energy storage system with a set of input variables.

Author Contributions: Conceptualization, A.L. and A.C.Y.Y.; methodology, A.L. and W.W. (Wei Wang);
software, T.B.Y.C.; validation, A.L. and A.C.Y.Y.; formal analysis, A.L. and C.S.L.; investigation, W.W.
(Wei Wang); resources, T.B.Y.C. and W.W. (Wei Wu); data curation, W.Y.; writing—original draft
preparation, A.L.; writing—review and editing, Q.N.C. and S.K.; visualization, A.L.; supervision,
G.H.Y.; project administration, A.C.Y.Y.; funding acquisition, G.H.Y. All authors have read and agreed
to the published version of the manuscript.
Funding: This research was funded by the Australian Research Council (ARC Industrial Transfor-
mation Training Centre IC170100032) and the Australian Government Research Training Program
Scholarship. The authors deeply appreciate all financial and technical supports.
Conflicts of Interest: The authors declare no conflict of interest.

References
1. Yang, Y.; Bremner, S.; Menictas, C.; Kay, M. Battery energy storage system size determination in renewable energy systems: A
review. Renew. Sustain. Energy Rev. 2018, 91, 109–125. [CrossRef]
2. Armand, M.; Axmann, P.; Bresser, D.; Copley, M.; Edström, K.; Ekberg, C.; Guyomard, D.; Lestriez, B.; Novák, P.; Petranikova, M.
Lithium-ion batteries–Current state of the art and anticipated developments. J. Power Sour. 2020, 479, 228708. [CrossRef]
3. Li, Y.; Vilathgamuwa, M.; Xiong, B.; Tang, J.; Su, Y.; Wang, Y. Design of minimum cost degradation-conscious lithium-ion battery
energy storage system to achieve renewable power dispatchability. Appl. Energy 2020, 260, 114282. [CrossRef]
4. Chen, T.; Jin, Y.; Lv, H.; Yang, A.; Liu, M.; Chen, B.; Xie, Y.; Chen, Q. Applications of lithium-ion batteries in grid-scale energy
storage systems. Trans. Tianjin Univ. 2020, 26, 208–217. [CrossRef]
5. Lai, C.S.; Jia, Y.; Xu, Z.; Lai, L.L.; Li, X.; Cao, J.; McCulloch, M.D. Levelized cost of electricity for photovoltaic/biogas power plant
hybrid system with electrical energy storage degradation costs. Energy Convers. Manag. 2017, 153, 34–47. [CrossRef]
Batteries 2022, 8, 69 16 of 17

6. Zhang, C.; Jiang, J.; Gao, Y.; Zhang, W.; Liu, Q.; Hu, X. Charging optimization in lithium-ion batteries based on temperature rise
and charge time. Appl. Energy 2017, 194, 569–577. [CrossRef]
7. Dong, G.; Wei, J. Determination of the load capability for a lithium-ion battery pack using two time-scale filtering. J. Power Sour.
2020, 480, 229056. [CrossRef]
8. Xia, Q.; Wang, Z.; Ren, Y.; Yang, D.; Sun, B.; Feng, Q.; Qian, C. Performance reliability analysis and optimization of lithium-ion
battery packs based on multiphysics simulation and response surface methodology. J. Power Sour. 2021, 490, 229567. [CrossRef]
9. Feng, X.; Ouyang, M.; Liu, X.; Lu, L.; Xia, Y.; He, X. Thermal runaway mechanism of lithium ion battery for electric vehicles: A
review. Energy Storage Mater. 2018, 10, 246–267. [CrossRef]
10. Wang, Q.; Mao, B.; Stoliarov, S.I.; Sun, J. A review of lithium ion battery failure mechanisms and fire prevention strategies. Prog.
Energy Combust. Sci. 2019, 73, 95–131. [CrossRef]
11. Sun, P.; Bisschop, R.; Niu, H.; Huang, X. A review of battery fires in electric vehicles. Fire Technol. 2020, 56, 1–50. [CrossRef]
12. Li, A.; Yuen, A.C.Y.; Wang, W.; Cordeiro, I.M.d.; Wang, C.; Chen, T.B.Y.; Zhang, J.; Chan, Q.N.; Yeoh, G.H. A Review on
Lithium-Ion Battery Separators towards Enhanced Safety Performances and Modelling Approaches. Molecules 2021, 26, 478.
[CrossRef] [PubMed]
13. Akinlabi, A.H.; Solyali, D. Configuration, design, and optimization of air-cooled battery thermal management system for electric
vehicles: A review. Renew. Sustain. Energy Rev. 2020, 125, 109815. [CrossRef]
14. Jiang, Z.; Li, H.; Qu, Z.; Zhang, J. Recent progress in lithium-ion battery thermal management for a wide range of temperature
and abuse conditions. Int. J. Hydrog. Energy 2022, 47, 9428–9459. [CrossRef]
15. Al-Zareer, M.; Dincer, I.; Rosen, M.A. Novel thermal management system using boiling cooling for high-powered lithium-ion
battery packs for hybrid electric vehicles. J. Power Sour. 2017, 363, 291–303. [CrossRef]
16. Smith, J.; Singh, R.; Hinterberger, M.; Mochizuki, M. Battery thermal management system for electric vehicle using heat pipes. Int.
J. Therm. Sci. 2018, 134, 517–529. [CrossRef]
17. Al-Zareer, M.; Dincer, I.; Rosen, M.A. Performance assessment of a new hydrogen cooled prismatic battery pack arrangement for
hydrogen hybrid electric vehicles. Energy Convers. Manag. 2018, 173, 303–319.
18. Saw, L.H.; Ye, Y.; Tay, A.A.; Chong, W.T.; Kuan, S.H.; Yew, M.C. Computational fluid dynamic and thermal analysis of Lithium-ion
battery pack with air cooling. Appl. Energy 2016, 177, 783–792.
19. Kirad, K.; Chaudhari, M. Design of cell spacing in lithium-ion battery module for improvement in cooling performance of the
battery thermal management system. J. Power Sour. 2021, 481, 229016. [CrossRef]
20. Shen, M.; Gao, Q. A review on battery management system from the modeling efforts to its multiapplication and integration. Int.
J. Energy Res. 2019, 43, 5042–5075. [CrossRef]
21. Deng, J.; Bae, C.; Marcicki, J.; Masias, A.; Miller, T. Safety modelling and testing of lithium-ion batteries in electrified vehicles. Nat.
Energy 2018, 3, 261–266. [CrossRef]
22. Cordeiro, I.M.D.C.; Liu, H.; Yuen, A.C.Y.; Chen, T.B.Y.; Li, A.; Cao, R.F.; Yeoh, G.H. Numerical investigation of expandable
graphite suppression on metal-based fire. Heat Mass Transf. 2021, 58, 1–17.
23. Xu, M.; Zhang, Z.; Wang, X.; Jia, L.; Yang, L. Two-dimensional electrochemical–thermal coupled modeling of cylindrical LiFePO4
batteries. J. Power Sour. 2014, 256, 233–243. [CrossRef]
24. Larsson, F.; Anderson, J.; Andersson, P.; Mellander, B.-E. Thermal modelling of cell-to-cell fire propagation and cascading thermal
runaway failure effects for lithium-ion battery cells and modules using fire walls. J. Electrochem. Soc. 2016, 163, A2854. [CrossRef]
25. Jin, X.; Duan, X.; Jiang, W.; Wang, Y.; Zou, Y.; Lei, W.; Sun, L.; Ma, Z. Structural design of a composite board/heat pipe based on
the coupled electro-chemical-thermal model in battery thermal management system. Energy 2021, 216, 119234. [CrossRef]
26. Wang, Z.; Fan, W.; Liu, P. Simulation of temperature field of lithium battery pack based on computational fluid dynamics. Energy
Procedia 2017, 105, 3339–3344. [CrossRef]
27. Wilke, S.; Schweitzer, B.; Khateeb, S.; Al-Hallaj, S. Preventing thermal runaway propagation in lithium ion battery packs using a
phase change composite material: An experimental study. J. Power Sour. 2017, 340, 51–59. [CrossRef]
28. An, Z.; Jia, L.; Li, X.; Ding, Y. Experimental investigation on lithium-ion battery thermal management based on flow boiling in
mini-channel. Appl. Therm. Eng. 2017, 117, 534–543. [CrossRef]
29. Ouyang, D.; Liu, J.; Chen, M.; Weng, J.; Wang, J. An experimental study on the thermal failure propagation in lithium-ion battery
pack. J. Electrochem. Soc. 2018, 165, A2184. [CrossRef]
30. Li, H.; Duan, Q.; Zhao, C.; Huang, Z.; Wang, Q. Experimental investigation on the thermal runaway and its propagation in the
large format battery module with Li (Ni1/3Co1/3Mn1/3) O2 as cathode. J. Hazard. Mater. 2019, 375, 241–254. [CrossRef]
31. Zhang, X.; Wang, Y.; Wu, J.; Chen, Z. A novel method for lithium-ion battery state of energy and state of power estimation based
on multi-time-scale filter. Appl. Energy 2018, 216, 442–451. [CrossRef]
32. Li, K.; Yan, J.; Chen, H.; Wang, Q. Water cooling based strategy for lithium ion battery pack dynamic cycling for thermal
management system. Appl. Therm. Eng. 2018, 132, 575–585. [CrossRef]
33. Zhao, R.; Zhang, S.; Liu, J.; Gu, J. A review of thermal performance improving methods of lithium ion battery: Electrode
modification and thermal management system. J. Power Sour. 2015, 299, 557–577. [CrossRef]
34. Kim, J.; Oh, J.; Lee, H. Review on battery thermal management system for electric vehicles. Appl. Therm. Eng. 2019, 149, 192–212.
[CrossRef]
Batteries 2022, 8, 69 17 of 17

35. Patel, J.R.; Rathod, M.K. Recent developments in the passive and hybrid thermal management techniques of lithium-ion batteries.
J. Power Sour. 2020, 480, 228820. [CrossRef]
36. Fan, L.; Khodadadi, J.; Pesaran, A. A parametric study on thermal management of an air-cooled lithium-ion battery module for
plug-in hybrid electric vehicles. J. Power Sour. 2013, 238, 301–312. [CrossRef]
37. Wang, T.; Tseng, K.; Zhao, J.; Wei, Z. Thermal investigation of lithium-ion battery module with different cell arrangement
structures and forced air-cooling strategies. Appl. Energy 2014, 134, 229–238. [CrossRef]
38. Choudhari, V.; Dhoble, A.; Panchal, S. Numerical analysis of different fin structures in phase change material module for battery
thermal management system and its optimization. Int. J. Heat Mass Transf. 2020, 163, 120434. [CrossRef]
39. Chen, S.; Peng, X.; Bao, N.; Garg, A. A comprehensive analysis and optimization process for an integrated liquid cooling plate for
a prismatic lithium-ion battery module. Appl. Therm. Eng. 2019, 156, 324–339. [CrossRef]
40. Mitchell, T.M. Machine Learning; McGraw-hill: New York, NY, USA, 1997.
41. Jaliliantabar, F.; Mamat, R.; Kumarasamy, S. Prediction of lithium-ion battery temperature in different operating conditions
equipped with passive battery thermal management system by artificial neural networks. Mater. Today Proc. 2022, 48, 1796–1804.
[CrossRef]
42. Wu, B.; Han, S.; Shin, K.G.; Lu, W. Application of artificial neural networks in design of lithium-ion batteries. J. Power Sour. 2018,
395, 128–136. [CrossRef]
43. Qian, X.; Xuan, D.; Zhao, X.; Shi, Z. Heat dissipation optimization of lithium-ion battery pack based on neural networks. Appl.
Therm. Eng. 2019, 162, 114289. [CrossRef]
44. Feng, F.; Teng, S.; Liu, K.; Xie, J.; Xie, Y.; Liu, B.; Li, K. Co-estimation of lithium-ion battery state of charge and state of temperature
based on a hybrid electrochemical-thermal-neural-network model. J. Power Sour. 2020, 455, 227935. [CrossRef]
45. Shi, Y.; Ahmad, S.; Liu, H.; Lau, K.T.; Zhao, J. Optimization of air-cooling technology for LiFePO4 battery pack based on deep
learning. J. Power Sour. 2021, 497, 229894. [CrossRef]
46. Guo, M.; Sikha, G.; White, R.E. Single-particle model for a lithium-ion cell: Thermal behavior. J. Electrochem. Soc. 2010, 158, A122.
[CrossRef]
47. Doyle, M.; Newman, J.; Gozdz, A.S.; Schmutz, C.N.; Tarascon, J.M. Comparison of modeling predictions with experimental data
from plastic lithium ion cells. J. Electrochem. Soc. 1996, 143, 1890. [CrossRef]
48. Chen, S.-C.; Wang, Y.-Y.; Wan, C.-C. Thermal analysis of spirally wound lithium batteries. J. Electrochem. Soc. 2006, 153, A637.
[CrossRef]
49. Chen, M.; Challita, U.; Saad, W.; Yin, C.; Debbah, M. Artificial neural networks-based machine learning for wireless networks: A
tutorial. IEEE Commun. Surv. Tutor. 2019, 21, 3039–3071. [CrossRef]
50. Hunter, D.; Yu, H.; Pukish, M.S., III; Kolbusz, J.; Wilamowski, B.M. Selection of proper neural network sizes and architectures—A
comparative study. IEEE Trans. Ind. Inform. 2012, 8, 228–240. [CrossRef]
51. ToolBox, E. Convective Heat Transfer. Available online: https://www.engineeringtoolbox.com/convective-heat-transfer-d_430.
html (accessed on 27 July 2021).
52. Hagan, M.T.; Menhaj, M.B. Training feedforward networks with the Marquardt algorithm. IEEE Trans. Neural Netw. 1994, 5,
989–993. [CrossRef]
53. Levenberg, K. A method for the solution of certain non-linear problems in least squares. Q. Appl. Math. 1944, 2, 164–168.
[CrossRef]
54. Marquardt, D.W. An algorithm for least-squares estimation of nonlinear parameters. J. Soc. Ind. Appl. Math. 1963, 11, 431–441.
[CrossRef]
55. Yetik, O.; Karakoc, T.H. Estimation of thermal effect of different busbars materials on prismatic Li-ion batteries based on artificial
neural networks. J. Energy Storage 2021, 38, 102543. [CrossRef]